Beta
ManageSearchChatDiscover
284717

Re-Talk: Automated Speech Assistance for People with Dysarthria

Article

Last updated: 26 Dec 2024

OverviewSimilar Items

Subjects

-

Tags

-

Abstract

Dysarthria is a speech motor disorder where the muscles responsible for speech production, such as in the face, mouth, or respiratory system, have trouble coordinating and controlling themselves. Our research goal is to help individuals with dysarthria communicate effectively. Often, physical conditions make it challenging for them to express their thoughts through writing. Our research introduces an automatic speech assistant solution, consisting of two main parts: speech recognition and auto-correct. The speech recognition component takes the person's distorted speech as input, converts it to text, and then sends it to the auto-correct module to fix any mistakes or unclear words. We tested our model on both English and Arabic datasets. The English dataset showed a 50% Word Error Rate (WER) which was reduced to 40% after using the auto-correct module. Our results outperformed previous studies by 4.5%. However, the WER on the Arabic dataset was 80% which is not a satisfactory result, due to the limited size of the Egyptian Dialect Dysarthric Speech (EDDS) database.  

DOI

10.21608/fcihib.2023.188592.1077

Keywords

DSR, B-LSTM, CNN-LSTM, UASpeech Database, Auto Correction

Authors

First Name

Salma Khaled

Last Name

Ali

MiddleName

-

Affiliation

Computer Science, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt.

Email

salmakhaled708@gmail.com

City

-

Orcid

-

First Name

Aya Mohamed

Last Name

Hassan

MiddleName

-

Affiliation

Computer Science, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt.

Email

ayhassan@nu.edu.eg

City

-

Orcid

-

First Name

Ahmed Mohamed

Last Name

Salah

MiddleName

-

Affiliation

Computer Science, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt.

Email

ahmed.mohamadsalah@gmail.com

City

-

Orcid

-

First Name

Donia Wael

Last Name

Mohamed

MiddleName

-

Affiliation

Computer Science, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt.

Email

doniawaelsamir@gmail.com

City

-

Orcid

-

First Name

Muhammed

Last Name

Mustafa

MiddleName

-

Affiliation

Computer Science, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt.

Email

muhammedmuustafa@gmail.com

City

-

Orcid

-

First Name

Ensaf Hussein

Last Name

Mohamed

MiddleName

-

Affiliation

Computer Science, Faculty of Computers and Artificial Intelligence, Helwan University, Cairo, Egypt.

Email

ensaf_hussein@fci.helwan.edu.eg

City

-

Orcid

0000-0002-1615-0236

Volume

5

Article Issue

1

Related Issue

38999

Issue Date

2023-01-01

Receive Date

2023-01-20

Publish Date

2023-01-31

Page Start

16

Page End

22

Print ISSN

2537-0901

Online ISSN

2535-1397

Article File

FCIHIB_Volume 5_Issue 1_Pages 16-22.pdf

PDF . 729.3kB

Link

https://fcihib.journals.ekb.eg/article_284717.html

Detail API

https://fcihib.journals.ekb.eg/service?article_code=284717

Order

284,717

Type

المقالة الأصلية

Type Code

1,411

Publication Type

Journal

Publication Title

النشرة المعلوماتية في الحاسبات والمعلومات

Publication Link

https://fcihib.journals.ekb.eg/

MainTitle

Re-Talk: Automated Speech Assistance for People with Dysarthria

Details

Type

Article

Created At

26 Dec 2024